Bacharelado em Sistemas de Informação (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/12
Siglas das Coleções:
APP - Artigo Publicado em Periódico
TAE - Trabalho Apresentado em Evento
TCC - Trabalho de Conclusão de Curso
Navegar
17 resultados
Resultados da Pesquisa
Item Previsão de preço de ações de empresas do setor elétrico com algoritmos de aprendizado de máquina(2025-03-21) Silva, Herculles Hendrius Coutinho Mesquita; Albuquerque Júnior, Gabriel Alves de; http://lattes.cnpq.br/1399502815770584O presente trabalho tem como objetivo comparar a eficiência de diferentes algoritmos de aprendizado de máquina na previsão de preços de ações do setor de energia elétrica. Para isso, foram analisados quatro algoritmos: Long Short-Term Memory (LSTM), Support Vector Regression (SVR), Regressão Linear e Random Forest. Os dados utilizados compreendem uma série histórica de preços e indicadores adicionais, como inflação, Índice de energia elétrica (IEE) e variação cambial, que foram processados e utilizados como entrada para os modelos. A análise foi realizada com base em métricas de erro, como Erro Médio Absoluto (MAE), Erro Quadrático Médio (MSE) e Raiz do Erro Quadrático Médio (RMSE), bem como pela avaliação da diferença percentual entre os preços previstos e os valores reais. Os resultados mostram que o algoritmo LSTM obteve o melhor desempenho na previsão de preços de fechamento, seguido pela Regressão Linear, enquanto o Random Forest apresentou maior margem de erro e se monstrando inadequado para a aplicação neste problema. Este estudo realiza a aplicação de algoritmos preditivos no mercado financeiro, demonstrando o potencial do aprendizado de máquina como ferramenta para análise e tomada de decisão no setor de energia elétrica.Item Utilização de filtragem colaborativa no auxílio de recomendação personalizada para leitores de mangá(2024-03-04) Brochardt, Rodrigo Nativo do Brasil; Garrozi, Cícero; http://lattes.cnpq.br/0488054917286587This study investigated, developed, and compared two approaches for generating manga recommendations: the Singular Value Decomposition (SVD) model and the Pearson Correlation Coefficient. The methodology involved data preparation through the development and execution of a web scraper to extract manga information and reviews from a highly active internet forum. Challenges arising in the applicability of these data extraction methods were addressed, along with alternatives for handling source blocking situations, model training, and performance evaluation, focusing on collaborative filtering and personalized recommendations for user profiles and manga works. In the implementation of SVD, latent patterns in user review data were identified, enabling personalized recommendations based on individual preferences through the sharing of experiences with similar profiles. However, metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) revealed the need for model refinement to improve its accuracy, as well as alternative implementations for conducting comparisons and metrics related to the specific data mass used in the study. Conversely, the approach based on the Pearson Correlation Coefficient prioritized similarity between manga reviews to generate item-focused recommendations, although it significantly relied on the number of available reviews. This methodology offered a direct and valid logic for personalized recommendations based on relationships derived from reviews. The conclusion highlighted the future possibility of exploring hybrid methods combining the advantages of SVD and the Pearson Correlation Coefficient to achieve more precise and comprehensive recommendations, as well as validating techniques that bring different recommendation approaches for tangible comparison. The utilization of additional data gathered in the generated data mass to enrich the quality of recommendations was suggested, aiming to use more detailed parameters in recommendations, along with the employment of indirect approaches, such as using LLMs to aid in the recommendation process. Finally, the study emphasizes the importance of advancing these recommendation technologies to facilitate readers' lives by assisting in filtering the vast content offered by the industry and the internet.Item Processo de Renovação Generalizado baseado na distribuição Gumbel como modelo de estimativas de ocorrências de ondas de calor para auxiliar no processo de tomada de decisão do cultivo de manga no Sertão de Pernambuco(2023-05-08) Ferraz, Kimbelly Emanuelle Avelino; Cristino, Cláudio Tadeu; http://lattes.cnpq.br/0295290151219369; http://lattes.cnpq.br/2320958356149704Several types of events can harm the planting, harvesting or handling of plants and fruits in agricultural areas, one of them including the event called heat waves, which is characterized as a prolonged and relatively uncommon meteorological phenomenon with extremely high temperatures for the region and persistent for several days or even weeks. Given the importance of agriculture, this work seeks, through the analysis of the maximum temperature data in the Petrolina region, the study of the mango plantation, the Heat Wave event through the 90th percentile, optimization algorithms and the processes of generalized renewal and Gumbel, estimating this event contributing to the farmer’s decision making and optimization of Mango production. The proposed model uses the generalized renewal process based on the Gumbel distribution (GuGRP) to model the time intervals between heat waves, considering that consecutive events are conditionally independent. This model proved to be adherent to model events with a significance level of 0.05 and a P −V alue of 0.28 through the Kolmogorov-Smirnov adherence test on the adequacy data adapted to the GuGRP. The model parameters were estimated by Log-Likelihood using optimization algorithms, also specifically testing the Particle Swarm algorithm.Item Implementação WebGIS para análise de mercado e processo de compra e venda(2020-11-05) Alves, Allan do Amaral; Gouveia, Roberta Macêdo Marques; Batista, Maria da Conceição Moraes; http://lattes.cnpq.br/8167265341219263; http://lattes.cnpq.br/2024317361355224; http://lattes.cnpq.br/8469386114225610With the growing use of e-commerce platforms in the country and the various economic crises affecting the number of establishments sales since 2014, small and large retail companies are faced with the need to carry out an increasingly careful analysis of the environment in which they are located, in order to identify potential buyers of products in profile, geographic location and other attributes to optimize the direction of your services, anticipating possible changes in demand and obtaining a lower risk in association to the investments made. With the current technology, geographic information systems have become allies for the study of large databases, generating results that help the decision making of these companies. This work aims to implement a WEBGIS application for data analysis and rescue of significant geographical information, using a clustering algorithm to calculate and simulate improvement scenarios, identify regions with more buyers and indicate the best locations for selling classified products in different sectors of the market. metropolitan region of Recife using data from electronic invoices.Item Explainable Artificial Intelligence - uma análise dos trade-offs entre desempenho e explicabilidade(2023-08-18) Assis, André Carlos Santos de; Andrade, Ermeson Carneiro de; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/2466077615273972; http://lattes.cnpq.br/3963132175829207Explainability is essential for users to efficiently understand, trust, and manage computer systems that use artificial intelligence. Thus, as well as assertiveness, understanding how the decision-making process of the models occurred is fundamental. While there are studies that focus on the explainability of artificial intelligence algorithms, it is important to highlight that, as far as we know, none of them have comprehensively analyzed the trade-offs between performance and explainability. In this sense, this research aims to fill this gap by investigating both transparent algorithms, such as Decision Tree and Logistic Regression, and opaque algorithms, such as Random Forest and Support Vector Machine, in order to evaluate the trade-offs between performance and explainability. The results reveal that opaque algorithms have a low explanability and do not perform well regarding response time due to their complexity, but are more assertive. On the other hand, transparent algorithms have a more effective explainability and better performance regarding response time, but in our experiments, we observed that accuracy obtained was lower than the accuracy of opaque models.Item Recomendação de psicólogos por meio de algoritmos de filtragem colaborativa, conteúdo e híbrida(2023-09-14) Gomes Júnior, Augusto Rosário; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863There is a rising number of people diagnosed with mental health disorders such as depression and anxiety, disorders that have been long neglected by science and society. Even so, more and more advances are being made in the ways of treating these people, such as platforms that offer psychological care remotely. However, choosing a psychologist or therapist is not always an easy task, given the large amount of information involved in the choosing process. Based on that, the goal of this article was to develop a psychologist recommender system based on a hybrid model, which should be able to recommend psychologists with expertise that meet the needs of different types of patients. The model showed promising results, where the similarity between the recommended psychologists was consistent and good results were achieved in the evaluation metrics MAE (<0.5) and RMSE (<0.75). It was also possible to mitigate weaknesses from both content and collaborative recommendations.Item Sugestão de livros baseada em algoritmo híbrido de recomendação e grau de interesse recente(2023-05-26) Tavares, Eduardo Brandão; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863With a vast and growing range of books available, choose your next reading can become a complex job amid so many options. In the context of Brazil, where most readers have to choose well which book to buy, due to the low purchasing power of our population, an assertive recommendation has become more valuable. This article presents a book recommendation algorithm based on a hybrid model, which consists of using both techniques related to association rules and techniques that are based on the content of books, aiming to present unknown books that follow the recent interest of the reader. The model managed to reach an accuracy comparable to other models in the RMSE and MAE metrics and delivers recommendations closely related to the last readings of each reader.Item Análise das dinâmicas de transmissão da Mpox em Pernambuco através do uso de Modelo SEIQR com otimização de parâmetros(2022-11-23) Pessoa, Wagner Palacio; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863; http://lattes.cnpq.br/0525335441263931In recent years, as a result of the COVID-19 pandemic, the importance of the accuracy of the results of studies related to the evolution and propagation of diseases has become evident, so that scientific authorities have enough inputs to make quick decisions in the containment and prevention of epidemics and mitigate their effects on society and the economy as soon as possible. At the end of July 2022, the Mpox (Monkeypox) outbreak was declared a global health emergency by the WHO, accelerating a possible return to the state of alert for a new pandemic. This work aims to analyze the transmission dynamics of this virus in Pernambuco using the SEIQR compartmental epidemiological model (Susceptible, Exposed, Infected, Quarantineed and Recovered), with data available from July 12 to November 3, 2022. The simulations were performed with the Wolfram Language. Experiments were performed with manual adjustment of the model parameters by a graphical interface and also considering the dynamic adjustment over time intervals, using a non-linear optimization function. The results suggest a possible regression in the spread of the virus in the state between mid-December 2022 and January 2023.Item Detecção de anomalias em dados meteorológicos do sertão de Pernambuco utilizando Isolation Forest e DBSCAN(2022-06-02) Cavalcante, Anderson Rodrigues; Medeiros, Victor Wanderley Costa de; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/0155290293799371Anomalous values are one of the problems present in the Big Data age. Robust techniques are required to manipulate correct and incorrect information that is generated at each time. Using non-supervised machine learning algorithms gives the confidence of good performance in the final results. This research will use meteorological data on air temperature and relative humidity from the Instituto Nacional de Meteorologia, of Petrolina, with DBSCAN (Density Based Spatial Clustering of Application with Noise) and IF (Isolation Forest) implemented to detect anomalies present in the data, since weathering meteorological anomalies may appear through defects, bad sensor configuration and even extreme climate effects.Item Vinculando perfis de engajamento ao desempenho acadêmico por meio de análise de redes sociais e análise de agrupamento nos dados de fóruns de discussão(2021-11-18) Oliveira, Pamella Letícia Silva de; Rodrigues, Rodrigo Lins; http://lattes.cnpq.br/5512849006877767; http://lattes.cnpq.br/8863320225621574